{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":30664,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-03-12T07:15:18.695081Z","iopub.execute_input":"2024-03-12T07:15:18.695512Z","iopub.status.idle":"2024-03-12T07:15:20.315447Z","shell.execute_reply.started":"2024-03-12T07:15:18.695477Z","shell.execute_reply":"2024-03-12T07:15:20.313629Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"mnist_train = pd.read_csv(\"../input/digit-recognizer/train.csv\")\nmnist_test = pd.read_csv(\"../input/digit-recognizer/test.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:15:33.589781Z","iopub.execute_input":"2024-03-12T07:15:33.590239Z","iopub.status.idle":"2024-03-12T07:15:38.816550Z","shell.execute_reply.started":"2024-03-12T07:15:33.590205Z","shell.execute_reply":"2024-03-12T07:15:38.815206Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_train1 = pd.get_dummies(mnist_train.label)\nprint(y_train1.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:15:44.412714Z","iopub.execute_input":"2024-03-12T07:15:44.413571Z","iopub.status.idle":"2024-03-12T07:15:44.432008Z","shell.execute_reply.started":"2024-03-12T07:15:44.413533Z","shell.execute_reply":"2024-03-12T07:15:44.430444Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"npx = mnist_train.drop(['label'], axis=1)\nx_train1 = np.array(npx).reshape(42000,28,28,1)/255\nprint(x_train1.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:15:49.157219Z","iopub.execute_input":"2024-03-12T07:15:49.157744Z","iopub.status.idle":"2024-03-12T07:15:49.539045Z","shell.execute_reply.started":"2024-03-12T07:15:49.157703Z","shell.execute_reply":"2024-03-12T07:15:49.537797Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split #to split our dataset\nx_train, x_val, y_train, y_val = train_test_split(x_train1, y_train1, test_size=0.1, random_state=101)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:16:01.087112Z","iopub.execute_input":"2024-03-12T07:16:01.087598Z","iopub.status.idle":"2024-03-12T07:16:01.543273Z","shell.execute_reply.started":"2024-03-12T07:16:01.087562Z","shell.execute_reply":"2024-03-12T07:16:01.542119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"npx = mnist_test\nx_test = np.array(npx).reshape(28000,28,28,1)/255\nprint(x_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:16:04.750530Z","iopub.execute_input":"2024-03-12T07:16:04.751518Z","iopub.status.idle":"2024-03-12T07:16:04.909561Z","shell.execute_reply.started":"2024-03-12T07:16:04.751477Z","shell.execute_reply":"2024-03-12T07:16:04.908302Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import keras\nprint(keras.__version__)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:17:09.207352Z","iopub.execute_input":"2024-03-12T07:17:09.208059Z","iopub.status.idle":"2024-03-12T07:17:09.213921Z","shell.execute_reply.started":"2024-03-12T07:17:09.208025Z","shell.execute_reply":"2024-03-12T07:17:09.212553Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.optimizers import Adam","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:17:45.936674Z","iopub.execute_input":"2024-03-12T07:17:45.937112Z","iopub.status.idle":"2024-03-12T07:17:45.942672Z","shell.execute_reply.started":"2024-03-12T07:17:45.937078Z","shell.execute_reply":"2024-03-12T07:17:45.941599Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pip install keras --upgrade","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:18:03.487020Z","iopub.execute_input":"2024-03-12T07:18:03.487477Z","iopub.status.idle":"2024-03-12T07:20:47.830690Z","shell.execute_reply.started":"2024-03-12T07:18:03.487442Z","shell.execute_reply":"2024-03-12T07:20:47.829130Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.utils import to_categorical","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:21:35.214415Z","iopub.execute_input":"2024-03-12T07:21:35.215023Z","iopub.status.idle":"2024-03-12T07:21:35.219822Z","shell.execute_reply.started":"2024-03-12T07:21:35.214991Z","shell.execute_reply":"2024-03-12T07:21:35.218686Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.layers import Conv2D, MaxPooling2D","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:22:19.539339Z","iopub.execute_input":"2024-03-12T07:22:19.539757Z","iopub.status.idle":"2024-03-12T07:22:19.545961Z","shell.execute_reply.started":"2024-03-12T07:22:19.539729Z","shell.execute_reply":"2024-03-12T07:22:19.544208Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import keras\nfrom keras.models import Sequential\nfrom keras.optimizers import Adam\nfrom keras.utils import to_categorical\nfrom keras.layers import Dense, Dropout, Flatten, BatchNormalization, Conv2D, MaxPooling2D\nfrom keras.preprocessing import image\nfrom keras.callbacks import ReduceLROnPlateau\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport cv2 \nfrom PIL import Image \n\nnp.random.seed(99)\n","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:23:39.017979Z","iopub.execute_input":"2024-03-12T07:23:39.018407Z","iopub.status.idle":"2024-03-12T07:23:39.025131Z","shell.execute_reply.started":"2024-03-12T07:23:39.018374Z","shell.execute_reply":"2024-03-12T07:23:39.024186Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def display(img):\n  plt.figure(figsize=(5,5))\n  plt.axis(\"off\")\n  plt.imshow(img,cmap=\"gray\")\n\ndisplay(x_train[1191])","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:23:43.310449Z","iopub.execute_input":"2024-03-12T07:23:43.310869Z","iopub.status.idle":"2024-03-12T07:23:43.467778Z","shell.execute_reply.started":"2024-03-12T07:23:43.310834Z","shell.execute_reply":"2024-03-12T07:23:43.466525Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\ndatagen = ImageDataGenerator(rotation_range = 10, width_shift_range = 0.1, shear_range = 0.1,\n                             height_shift_range = 0.1, zoom_range = [0.9,1.1], fill_mode = 'nearest', \n                             horizontal_flip = False, vertical_flip = False)\ndatagen.fit(x_train)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:23:52.073516Z","iopub.execute_input":"2024-03-12T07:23:52.073894Z","iopub.status.idle":"2024-03-12T07:23:52.171011Z","shell.execute_reply.started":"2024-03-12T07:23:52.073865Z","shell.execute_reply":"2024-03-12T07:23:52.169779Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def Conv_Net_model():\n  model = Sequential()\n  model.add(Conv2D(32,(3,3), input_shape=(28,28,1), padding=\"same\", activation=\"relu\"))\n  model.add(MaxPooling2D(pool_size=(2,2)))\n  model.add(BatchNormalization(axis = -1))\n  model.add(Conv2D(64,(3,3), activation=\"relu\", padding=\"same\"))\n  model.add(MaxPooling2D(pool_size=(2,2)))\n  model.add(BatchNormalization(axis = -1))\n  model.add(Flatten())\n  model.add(Dense(200, activation=\"relu\"))\n  model.add(BatchNormalization(axis = -1))\n  model.add(Dropout(rate=0.4))\n  model.add(Dense(100, activation=\"relu\"))\n  model.add(BatchNormalization(axis = -1))\n  model.add(Dropout(rate=0.4))\n  model.add(Dense(10, activation=\"softmax\"))\n  return model\n\nmodel = Conv_Net_model()\nprint(model.summary())","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:24:08.120955Z","iopub.execute_input":"2024-03-12T07:24:08.121488Z","iopub.status.idle":"2024-03-12T07:24:08.419645Z","shell.execute_reply.started":"2024-03-12T07:24:08.121443Z","shell.execute_reply":"2024-03-12T07:24:08.418335Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"reduce_lr = ReduceLROnPlateau(monitor = 'val_accuracy', \n                              min_lr = 0.00001, verbose = 1,  patience = 2, factor = 0.7, mode = 'auto', cooldown = 0)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:24:21.533547Z","iopub.execute_input":"2024-03-12T07:24:21.533936Z","iopub.status.idle":"2024-03-12T07:24:21.540041Z","shell.execute_reply.started":"2024-03-12T07:24:21.533908Z","shell.execute_reply":"2024-03-12T07:24:21.538532Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense, Flatten, Conv2D, MaxPooling2D\n\n# Membuat model\nmodel = Sequential()\nmodel.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1)))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dense(10, activation='softmax'))\n\n# Mengkompilasi model\nmodel.compile(loss='categorical_crossentropy', optimizer=Adam(learning_rate=0.001), metrics=['accuracy'])\n\n# Melatih model\nmodel.fit(x_train, y_train, validation_data=(x_val, y_val), epochs=10, batch_size=128)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:24:25.343395Z","iopub.execute_input":"2024-03-12T07:24:25.343789Z","iopub.status.idle":"2024-03-12T07:26:07.227498Z","shell.execute_reply.started":"2024-03-12T07:24:25.343760Z","shell.execute_reply":"2024-03-12T07:26:07.226227Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred=model.predict(x_test)\ny_test = np.argmax(y_pred,axis=1)\nprint(y_test.shape)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:26:16.520068Z","iopub.execute_input":"2024-03-12T07:26:16.520503Z","iopub.status.idle":"2024-03-12T07:26:21.068742Z","shell.execute_reply.started":"2024-03-12T07:26:16.520470Z","shell.execute_reply":"2024-03-12T07:26:21.067464Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample = pd.read_csv(\"../input/digit-recognizer/sample_submission.csv\")\ni = sample.ImageId\n\noutput = pd.DataFrame({'ImageId' : i,'Label': y_test})\noutput.head(20)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:26:26.401786Z","iopub.execute_input":"2024-03-12T07:26:26.402253Z","iopub.status.idle":"2024-03-12T07:26:26.440179Z","shell.execute_reply.started":"2024-03-12T07:26:26.402216Z","shell.execute_reply":"2024-03-12T07:26:26.438955Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"display(x_test[18])","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:26:31.581517Z","iopub.execute_input":"2024-03-12T07:26:31.581959Z","iopub.status.idle":"2024-03-12T07:26:31.693459Z","shell.execute_reply.started":"2024-03-12T07:26:31.581925Z","shell.execute_reply":"2024-03-12T07:26:31.691421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"output.to_csv('submission.csv', index=False)","metadata":{"execution":{"iopub.status.busy":"2024-03-12T07:26:36.520889Z","iopub.execute_input":"2024-03-12T07:26:36.521359Z","iopub.status.idle":"2024-03-12T07:26:36.568957Z","shell.execute_reply.started":"2024-03-12T07:26:36.521313Z","shell.execute_reply":"2024-03-12T07:26:36.567985Z"},"trusted":true},"execution_count":null,"outputs":[]}]}